Deep Learning to Estimate RECIST in Patients with NSCLC Treated with PD-1 Blockade.

Real-world evidence (RWE), conclusions derived from analysis of patients not treated in clinical trials, is increasingly recognized as an opportunity for discovery, to reduce disparities, and to contribute to regulatory approval. Maximal value of RWE may be facilitated through machine-learning techniques to integrate and interrogate large and otherwise underutilized datasets. In cancer research, an ongoing challenge for RWE is the lack of reliable, reproducible, scalable assessment of treatment-specific outcomes. We hypothesized a deep-learning model could be trained to use radiology text reports to estimate gold-standard RECIST-defined outcomes. Using text reports from patients with non-small cell lung cancer treated with PD-1 blockade in a training cohort and two test cohorts, we developed a deep-learning model to accurately estimate best overall response and progression-free survival. Our model may be a tool to determine outcomes at scale, enabling analyses of large clinical databases. SIGNIFICANCE: We developed and validated a deep-learning model trained on radiology text reports to estimate gold-standard objective response categories used in clinical trial assessments. This tool may facilitate analysis of large real-world oncology datasets using objective outcome metrics determined more reliably and at greater scale than currently possible.This article is highlighted in the In This Issue feature, p. 1.

Holistic Multi-modal Memory Network for Movie Question Answering.

Answering questions using multi-modal context is a challenging problem as it requires a deep integration of diverse data sources. Existing approaches only consider a subset of all possible interactions among data sources during one attention hop. In this paper, we present a Holistic Multi-modal Memory Network (HMMN) framework that fully considers interactions between different input sources (multi-modal context, question) at each hop. In addition, to hone in on relevant information, our framework takes answer choices into consideration during the context retrieval stage. Our HMMN framework effectively integrates information from the multi-modal context, question, and answer choices, enabling more informative context to be retrieved for question answering. Experimental results on the MovieQA and TVQA datasets validate the effectiveness of our HMMN framework. Extensive ablation studies show the importance of holistic reasoning and reveal the contributions of different attention strategies to model performance.

Audio-Tactile Skinny Buttons for Touch User Interfaces.

This study proposes a novel skinny button with multimodal audio and haptic feedback to enhance the touch user interface of electronic devices. The active material in the film-type actuator is relaxor ferroelectric polymer (RFP) poly(vinylidene fluoride-trifluoroethylene-chlorofluoroethylene) [P(VDF-TrFE-CFE)] blended with poly(vinylidene fluoride-trifluoroethylene) [P(VDF-TrFE)], which produces mechanical vibrations via the fretting vibration phenomenon. Normal pressure applied by a human fingertip on the film-type skinny button mechanically activates the locally concentrated electric field under the contact area, thereby producing a large electrostrictive strain in the blended RFP film. Multimodal audio and haptic feedback is obtained by simultaneously applying various electric signals to the pairs of ribbon-shaped top and bottom electrodes. The fretting vibration provides tactile feedback at frequencies of 50-300 Hz and audible sounds at higher frequencies of 500 Hz to 1 kHz through a simple on-off mechanism. The advantage of the proposed audio-tactile skinny button is that it restores the "click" sensation to the popular virtual touch buttons employed in contemporary electronic devices.

N-Benzoyl dithieno[3,2-b:2',3'-d]pyrrole-based hyperbranched polymers by direct arylation polymerization.

BACKGROUND: Although poly(N-acyl dithieno[3,2-b:2',3'-d]pyrrole)s have attracted great attention as a new class of conducting polymers with highly stabilized energy levels, hyperbranched polymers based on this monomer type have not yet been studied. Thus, this work aims at the synthesis of novel hyperbranched polymers containing N-benzoyl dithieno[3,23,2-b:2',3'-d]pyrrole acceptor unit and 3-hexylthiophene donor moiety via the direct arylation polymerization method. Their structures, molecular weights and thermal properties were characterized via 1H NMR and FTIR spectroscopies, GPC, TGA, DSC and XRD measurements, and the optical properties were investigated by UV-vis and fluorescence spectroscopies. RESULTS: Hyperbranched conjugated polymers containing N-benzoyl dithieno[3,23,2-b:2',3'-d]pyrrole acceptor unit and 3-hexylthiophene donor moiety, linked with either triphenylamine or triphenylbenzene as branching unit, were obtained via direct arylation polymerization of the N-benzoyl dithieno[3,23,2-b:2',3'-d]pyrrole, 2,5-dibromo 3-hexylthiophene and tris(4-bromophenyl)amine (or 1,3,5-tris(4-bromophenyl)benzene) monomers. Organic solvent-soluble polymers with number-average molecular weights of around 18,000 g mol-1 were obtained in 80-92% yields. The DSC and XRD results suggested that the branching structure hindered the stacking of polymer chains, leading to crystalline domains with less ordered packing in comparison with the linear analogous polymers. The results revealed that the hyperbranched polymer with triphenylbenzene as the branching unit exhibited a strong red-shift of the maximum absorption wavelength, attributed to a higher polymer stacking order as a result of the planar structure of triphenylbenzene. CONCLUSION: Both hyperbranched polymers with triphenylamine/triphenylbenzene as branching moieties exhibited high structural order in thin films, which can be promising for organic solar cell applications. The UV-vis absorption of the hyperbranched polymer containing triphenylbenzene as branching unit was red-shifted as compared with the triphenylamine-containing polymer, as a result of a higher chain packing degree.

Overview of the gene ontology task at BioCreative IV.

Gene ontology (GO) annotation is a common task among model organism databases (MODs) for capturing gene function data from journal articles. It is a time-consuming and labor-intensive task, and is thus often considered as one of the bottlenecks in literature curation. There is a growing need for semiautomated or fully automated GO curation techniques that will help database curators to rapidly and accurately identify gene function information in full-length articles. Despite multiple attempts in the past, few studies have proven to be useful with regard to assisting real-world GO curation. The shortage of sentence-level training data and opportunities for interaction between text-mining developers and GO curators has limited the advances in algorithm development and corresponding use in practical circumstances. To this end, we organized a text-mining challenge task for literature-based GO annotation in BioCreative IV. More specifically, we developed two subtasks: (i) to automatically locate text passages that contain GO-relevant information (a text retrieval task) and (ii) to automatically identify relevant GO terms for the genes in a given article (a concept-recognition task). With the support from five MODs, we provided teams with >4000 unique text passages that served as the basis for each GO annotation in our task data. Such evidence text information has long been recognized as critical for text-mining algorithm development but was never made available because of the high cost of curation. In total, seven teams participated in the challenge task. From the team results, we conclude that the state of the art in automatically mining GO terms from literature has improved over the past decade while much progress is still needed for computer-assisted GO curation. Future work should focus on addressing remaining technical challenges for improved performance of automatic GO concept recognition and incorporating practical benefits of text-mining tools into real-world GO annotation. DATABASE URL: http://www.biocreative.org/tasks/biocreative-iv/track-4-GO/.